© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 16548
    Prev
    Next
    INDEX
    Explanations

    django csrf exempt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mother
    -0.11
     Kings
    -0.10
     mos
    -0.10
     diplom
    -0.09
     conson
    -0.09
     Emin
    -0.09
     Walters
    -0.09
     anytime
    -0.09
     incon
    -0.09
     Hur
    -0.09
    POSITIVE LOGITS
    django
    0.21
     django
    0.19
    .djangoproject
    0.18
    .djang
    0.17
     Django
    0.16
     Dj
    0.13
    DJ
    0.13
     DJ
    0.13
     jsi
    0.12
     dj
    0.12
    Activations Density 0.018%

    No Known Activations